Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 18994
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures, specifically Hillary Clinton and Donald Trump

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mentions of political figures, particularly Hillary Clinton

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ++++++++++++++++
    -0.69
    BI
    -0.63
     helic
    -0.63
    âĸ¬âĸ¬
    -0.62
    Anyway
    -0.62
    meaning
    -0.61
    ãĥĢ
    -0.61
    GMT
    -0.61
    Product
    -0.60
    ãĥ¼ãĤ¯
    -0.59
    POSITIVE LOGITS
    enegger
    0.99
    hler
    0.87
    skirts
    0.87
     Jr
    0.85
    steen
    0.85
    Jr
    0.84
     Presents
    0.77
     campaigned
    0.76
    agher
    0.75
    atton
    0.73
    Activations Density 0.087%

    No Known Activations